检索结果-内蒙古大学图书馆

Image Orientation Estimation Based On Deep Learning - A Survey

Procedia Computer Science 2024年 242卷 1193-1197页

作者： Ruijie Xu Yong Shi Zhiquan Qi Research Center on Fictitious Economy and Data Science University of Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing 00190 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing 101408 China School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China College of Information Science and Technology University of Nebraska Omaha 68182 USA

In the realm of visual tasks, the estimation of orientation plays a pivotal role yet often remains an understudied aspect in the gamut of image analysis research. This paper endeavors to address this deficiency by conducting a comprehensive review of methods for orientation estimation within 2D imaging contexts. We aim to provide researchers with an exhaustive overview and detailed analysis of the techniques utilized for orientation estimation, thereby enhancing their understanding of this complex field. We introduce an organized classification of orientation estimation methods, segmented into approaches based on classification algorithms and those based on regression models. This classification not only sheds light on the distinct methodologies but also scrutinizes their underlying assumptions, practical applications. Additionally, the study identifies and underscores emerging research opportunities that hold the potential to enrich the discourse and technical advancements in orientation estimation, thereby encouraging deeper academic investigation and technological development.

关键词： Classification-based Orientation Estimation Regression-based Orientation Estimation

来源：评论

学校读者我要写书评

暂无评论

An ES-based model with contemporaneous and temporal aggregation for forecasting intermittent and lumpy retail demand

引用

Procedia Computer Science 2024年 242卷 264-271页

作者： Erjiang E Xin Tian Ye Tao Huiqiang Sun School of Management Guangxi Minzu University Nanning 530006 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy Sciences Beijing 100190 China Beijing Haolinju CVS Co. Ltd. Beijing 100018 China Shenghe (Beijing) Technology Development Co. Ltd. Beijing 101399 China

The demand for products in the retail industry is often characterized by intermittent and volatile patterns. Specifically, at the SKU level, the demand exhibits intermittent and lumpy behavior, which presents challenges for accurate forecasting due to demand fluctuations and interval uncertainty. This study proposes an exponential smoothing (ES)-based model, called ES-C-T, that incorporates contemporaneous and temporal aggregation to forecast intermittent and lumpy retail demand. The ES-C-T model consists of three stages. Firstly, the ES model predicts the sales of each product by aggregating contemporaneously across all stores, and the resulting predictions are allocated to the SKU level using a weight vector. Secondly, the ES model forecasts the sales of each SKU by aggregating temporally within each store. Finally, the ES-C-T model derives a weight coefficient based on the predictions from the first and second stages, adjusts the initial predictions, and utilizes this as the final forecast. To validate the effectiveness of the ES-C-T model, sales data from a large Chinese convenience store chain are employed. The results demonstrate that the proposed ES-C-T model outperforms the benchmark model in terms of MAE, RMSE, and WRMSSE, effectively predicting retail sales for intermittent and lumpy demand.

关键词： forecasting retailing intermittent demand lumpy demand aggregation

来源：评论

学校读者我要写书评

暂无评论

COVID-19 Impact on Global Electricity Generation Structure-Based on Sustainable Development Perspective

引用

Procedia computer science 2022年 214卷 1206-1213页

作者： Shuyang Peng Xian Yang Haibo Lu Kun Guo School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China. Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 China. Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China.

This paper has sorted out the general logic of the impact of COVID-19 on energy consumption. In the short term, the epidemic has forced governments to adopt different levels of lockdown measures. The total electricity consumption decreased and the share of renewable energy has increased. Based on the International Energy Agency's (IEA) data on electricity production and consumption, this paper analyzes the long-term effects: The COVID-19 pandemic does affect overall electricity demand and market structure in the short term, but in the long term, the impact of the pandemic is detrimental to the proportion of electricity generated from renewable sources. Increased, especially in hard-hit countries. The impact on countries with different levels of development is different, and countries with higher levels of economic development are better able to resist such exogenous shocks. The pandemic is still ongoing, how to steadily promote sustainable development? In this paper we suggest that to cope with climate change, to accomplish energy transformation and upgrading or even sustainable development, we should not only rely on reducing human activities, but give more support to countries with low development levels in realizing sustainable development.

关键词： COVID-19 Electricity generation Renewable energy

来源：评论

学校读者我要写书评

暂无评论

Poisoning Attack Against Estimating From Pairwise Comparisons

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2022年第10期44卷 6393-6408页

作者： Ma, Ke Xu, Qianqian Zeng, Jinshan Cao, Xiaochun Huang, Qingming Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 100049 Peoples R China Peng Cheng Lab Artificial Intelligence Res Ctr Shenzhen 518055 Guangdong Peoples R China Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China Jiangxi Normal Univ Sch Comp & Informat Engn Nanchang 330022 Jiangxi Peoples R China Chinese Acad Sci Inst Informat Engn State Key Lab Informat Secur SKLOIS Beijing 100093 Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing 100049 Peoples R China Univ Chinese Acad Sci Sch Econ & Management Key Lab Big Data Min & Knowledge Management Beijing 100049 Peoples R China

As pairwise ranking becomes broadly employed for elections, sports competitions, recommendation, information retrieval and so on, attackers have strong motivation and incentives to manipulate or disrupt the ranking list. They could inject malicious comparisons into the training data to fool the target ranking algorithm. Such a technique is called "poisoning attack" in regression and classification tasks. In this paper, to the best of our knowledge, we initiate the first systematic investigation of data poisoning attack on the pairwise ranking algorithms, which can be generally formalized as the dynamic and static games between the ranker and the attacker, and can be modeled as certain kinds of integer programming problems mathematically. To break the computational hurdle of the underlying integer programming problems, we reformulate them into the distributionally robust optimization (DRO) problems, which are computational tractable. Based on such DRO formulations, we propose two efficient poisoning attack algorithms and establish the associated theoretical guarantees including the existence of Nash equilibrium and the generalization ability bounds. The effectiveness of the suggested poisoning attack strategies is demonstrated by a series of toy simulations and several real data experiments. These experimental results show that the proposed methods can significantly reduce the performance of the ranker in the sense that the correlation between the true ranking list and the aggregated results with toxic data can be decreased dramatically.

关键词： Optimization Heuristic algorithms Sports Voting Uncertainty Games data models Adversarial learning poisoning attack pairwise comparison rank aggregation robust game distributionally robust optimization

来源：评论

学校读者我要写书评

暂无评论

A Review on the Construction of Business Intelligence System Based on Unstructured Image data

引用

Procedia Computer Science 2022年 199卷 392-398页

作者： Linzi Zhang Zhiquan Qi Fan Meng School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China Department of Infomation Management Peking University Beijing 100871 China

Business Intelligence (BI) has been an emerging significant issue in modern government and corporate functions, which attracts the attention of both researchers and merchants. Using the raw data from customers, BI provides effective decision-making knowledge for various cooperate governance operations with the method of data Warehouse and data mining. As the explosive growth of data volume, it has evolved into using unstructured data including image and text in business intelligence system, from the initial descriptive analysis of computational statements. This paper will review the methods of storing and analyzing the unstructured image data used in the construction of BI system, including traditional image processing and novel deep learning methods. In each method, the specific algorithms and application scenarios will be summarized. Together, we will discuss the possible innovative progress of BI system construction and its future trends.

关键词： Business intelligence Unstructured image data big data fusion

来源：评论

学校读者我要写书评

暂无评论

Clustering on hierarchical heterogeneous data with prior pairwise relationships

引用

BMC BIOINFORMATICS 2024年第1期25卷 40页

作者： Han, Wei Zhang, Sanguo Gao, Hailong Bu, Deliang Univ Chinese Acad Sci Sch Math Sci Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China Qingdao Univ Sch Math & Stat Qingdao Peoples R China Capital Univ Econ & Business Sch Stat Beijing Peoples R China

BackgroundClustering is a fundamental problem in statistics and has broad applications in various areas. Traditional clustering methods treat features equally and ignore the potential structure brought by the characteristic difference of features. Especially in cancer diagnosis and treatment, several types of biological features are collected and analyzed together. Treating these features equally fails to identify the heterogeneity of both data structure and cancer itself, which leads to incompleteness and inefficacy of current anti-cancer *** this paper, we propose a clustering framework based on hierarchical heterogeneous data with prior pairwise relationships. The proposed clustering method fully characterizes the difference of features and identifies potential hierarchical structure by rough and refined *** refined clustering further divides the clusters obtained by the rough clustering into different subtypes. Thus it provides a deeper insight of cancer that can not be detected by existing clustering methods. The proposed method is also flexible with prior information, additional pairwise relationships of samples can be incorporated to help to improve clustering performance. Finally, well-grounded statistical consistency properties of our proposed method are rigorously established, including the accurate estimation of parameters and determination of clustering *** proposed method achieves better clustering performance than other methods in simulation studies, and the clustering accuracy increases with prior information incorporated. Meaningful biological findings are obtained in the analysis of lung adenocarcinoma with clinical imaging data and omics data, showing that hierarchical structure produced by rough and refined clustering is necessary and reasonable.

关键词： Cancer clustering Hierarchy Heterogeneity Prior pairwise relationships

来源：评论

学校读者我要写书评

暂无评论

Optimizing Partial Area Under the Top-k Curve: Theory and Practice

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第4期45卷 5053-5069页

作者： Wang, Zitai Xu, Qianqian Yang, Zhiyong He, Yuan Cao, Xiaochun Huang, Qingming Chinese Acad Sci Inst Informat Engn State Key Lab Informat Secur Beijing 100093 Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing 100049 Peoples R China Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 100049 Peoples R China Alibaba Grp Secur Dept Hangzhou Peoples R China Sun Yat Sen Univ Sch Cyber Sci & Technol Shenzhen Campus Shenzhen 311121 Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 101408 Peoples R China Univ Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 101408 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China

Top-$k$k error has become a popular metric for large-scale classification benchmarks due to the inevitable semantic ambiguity among classes. Existing literature on top-$k$k optimization generally focuses on the optimization method of the top-$k$k objective, while ignoring the limitations of the metric itself. In this paper, we point out that the top-$k$k objective lacks enough discrimination such that the induced predictions may give a totally irrelevant label a top rank. To fix this issue, we develop a novel metric named partial Area Under the top-$k$k Curve (AUTKC). Theoretical analysis shows that AUTKC has a better discrimination ability, and its Bayes optimal score function could give a correct top-$K$K ranking with respect to the conditional probability. This shows that AUTKC does not allow irrelevant labels to appear in the top list. Furthermore, we present an empirical surrogate risk minimization framework to optimize the proposed metric. Theoretically, we present (1) a sufficient condition for Fisher consistency of the Bayes optimal score function;(2) a generalization upper bound which is insensitive to the number of classes under a simple hyperparameter setting. Finally, the experimental results on four benchmark datasets validate the effectiveness of our proposed framework.

关键词： Measurement Semantics Benchmark testing Training Loss measurement Fasteners Upper bound Machine learning label ambiguity Top-k error AUTKC optimization

来源：评论

学校读者我要写书评

暂无评论

MVQS: Robust multi-view instance-level cost-sensitive learning method for imbalanced data classification

引用

INFORMATION SCIENCES 2024年 675卷

作者： Hou, Zhaojie Tang, Jingjing Li, Yan Fu, Saiji Tian, Yingjie Southwestern Univ Finance & Econ Fac Business Adm Sch Business Adm Chengdu 611130 Peoples R China Southwestern Univ Finance & Econ Inst Big Data Chengdu 611130 Peoples R China Beijing Univ Posts & Telecommun Sch Econ & Management Beijing 100876 Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China UCAS MOE Social Sci Lab Digital Econ Forecasts & Policy Beijing 100190 Peoples R China

Multi-view imbalanced learning is to handle the datasets with multi-view representations and imbalanced classes. Existing multi-view imbalanced learning methods can be divided into two main categories: multi-view ensemble learning and multi-view cost-sensitive learning. However, these methods suffer from the following problems: 1) neglecting either consensus or complementary information, 2) complex preprocessing and information fusion in multiview ensemble learning and manual assignment of misclassification costs in multi-view costsensitive learning, and 3) limited ability to handle noisy samples. Therefore, we aim to design a concise and unified framework to grapple with the multi-view representations, imbalanced classes and noisy samples simultaneously. Inspired by the merits of support vector machine (SVM) and quadratic type squared error (QTSE) loss function, we propose a robust multi-view instance-level cost-sensitive SVM with QTSE loss (MVQS) for imbalanced data classification. The consensus regularization term and combination weight strategy are employed to fully exploit multi-view information. The QTSE loss can adaptively impose instance-level penalties to the misclassification of samples, and make MVQS be robust to noisy samples. We solve MVQS with the alternating direction method of multipliers (ADMM) and the gradient descent (GD) algorithm. Comprehensive experiments validate that MVQS is more competitive and robust than other benchmark approaches.

关键词： Multi-view learning Imbalanced classes Noisy samples Support vector machine QTSE loss function

来源：评论

学校读者我要写书评

暂无评论

USER: A Unified Information Search and Recommendation Model based on Integrated Behavior Sequence 21

USER: A Unified Information Search and Recommendation Model ...

引用

30th ACM International Conference on Information and knowledge management (CIKM)

作者： Yao, Jing Dou, Zhicheng Xie, Ruobing Lu, Yanxiong Wang, Zhiping Wen, Ji-Rong Renmin Univ China Gaoling Sch Artificial Intelligence Beijing Peoples R China WeChat Search Applicat Dept Tencent Peoples R China Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China MOE Key Lab Data Engn & Knowledge Engn Beijing Peoples R China

ISBN: (纸本)9781450384469

Search and recommendation are the two most common approaches used by people to obtain information. They share the same goal satisfying the user's information need at the right time. There are already a lot of Internet platforms and Apps providing both search and recommendation services, showing us the demand and opportunity to simultaneously handle both tasks. However, most platforms consider these two tasks independently - they tend to train separate search model and recommendation model, without exploiting the relatedness and dependency between them. In this paper, we argue that jointly modeling these two tasks will benefit both of them and finally improve overall user satisfaction. We investigate the interactions between these two tasks in the specific information content service domain. We propose first integrating the user's behaviors in search and recommendation into a heterogeneous behavior sequence, then utilizing a joint model for handling both tasks based on the unified sequence. More specifically, we design the Unified Information SEarch and Recommendation model (USER), which mines user interests from the integrated sequence and accomplish the two tasks in a unified way. Experiments on a dataset from a real-world information content service platform verify that our model outperforms separate search and recommendation baselines.

关键词： personalized search recommendation unified model

来源：评论

学校读者我要写书评

暂无评论

Deep Transformation Model

arXiv

引用

arXiv 2024年

作者： Wang, Tong Zhang, Shunqin Zhang, Sanguo Huang, Jian Ma, Shuangge Department of Biostatistics Yale School of Public Health New HavenCT United States School of Mathematical Sciences University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences China Department of Applied Mathematics The Hong Kong Polytechnic University Hong Kong

There has been a significant recent surge in deep neural network (DNN) techniques. Most of the existing DNN techniques have restricted model formats/assumptions. To overcome their limitations, we propose the nonparametric transformation model, which encompasses many popular models as special cases and hence is less sensitive to model mis-specification. This model also has the potential of accommodating heavy-tailed errors – a robustness property not broadly shared. Accordingly, a new loss function, which fundamentally differs from the existing ones, is developed. For computational feasibility, we further develop a double rectified linear unit (DReLU)based estimator. To accommodate the scenario with a diverging number of input variables and/or noises, we propose variable selection based on group penalization. We further expand the scope to coherently accommodate censored survival data. The estimation and variable selection properties are rigorously established. Extensive numerical studies, including simulations and data analyses, establish the satisfactory practical utility of the proposed methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

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：