检索结果-内蒙古大学图书馆

9th International Conference on Information Technology and Quantitative management, ITQM 2022

作者： Gu, Jifa Xiao, Xiao Zhang, Lingling Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China Moe Social Science Laboratory of Digital Economic Forecasts and Policy Simulation at Ucas Beijing100190 China

This paper introduces some modes from D, I, K to W, M. From different angles we investigate the various process. Especially we utilize the intelligent knowledge to develop the whole process. Finally we design a new medical hall for workshop of meta-synthetic engineering for helping patient to get the appropriate treatment and useful knowledge for health. © 2022 The Authors. Published by Elsevier B.V.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

D4M: dataset Distillation via Disentangled Diffusion Model

D4M: Dataset Distillation via Disentangled Diffusion Model

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Duo Su Junjie Hou Weizhi Gao Yingjie Tian Bowen Tang UCAS School of Computer Science and Technology Research Center on Fictitious Economy and Data Science CAS Key Laboratory of Big Data Mining and Knowledge Management CAS UCAS Sino-Danish College Department of Computer Science NCSU UCAS School of Economics and Management UCAS MOE Social Science Laboratory of Digital Economic Forecasts and Policy Simulation CAS Institute of Computing Technology

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

dataset distillation offers a lightweight synthetic dataset for fast network training with promising test accuracy. To imitate the performance of the original dataset, most approaches employ bi-level optimization and the distillation space relies on the matching architecture. Nevertheless, these approaches either suffer significant computational costs on large-scale datasets or experience performance decline on cross-architectures. We advocate for designing an economical dataset distillation framework that is independent of the matching architectures. With empirical observations, we argue that constraining the consistency of the real and synthetic image spaces will enhance the cross-architecture generalization. Motivated by this, we introduce dataset Distillation via Disentangled Diffusion Model (D 4 M), an efficient framework for dataset distillation. Compared to architecture-dependent methods, D 4 M employs latent diffusion model to guarantee consistency and incorporates label information into category prototypes. The distilled datasets are versatile, eliminating the need for repeated generation of distinct datasets for various architectures. Through comprehensive experiments, D4M demonstrates superior performance and robust generalization, surpassing the SOTA methods across most aspects.

关键词： Training Computer vision Computational modeling Prototypes Computer architecture Diffusion models Pattern recognition

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

Image Orientation Estimation Based On Deep Learning - A Survey

引用

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

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

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

MambaLCT: Boosting Tracking via Long-term Context State Space Model 39

MambaLCT: Boosting Tracking via Long-term Context State Spac...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Xiaohai Zhong, Bineng Liang, Qihua Li, Guorong Mo, Zhiyi Song, Shuxiang Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin 541004 China Guangxi Colleges Universities Key Laboratory of Intelligent Software Wuzhou University Wuzhou 543002 China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing 100101 China

ISBN: (纸本)157735897X

Effectively constructing context information with long-term dependencies from video sequences is crucial for object tracking. However, the context length constructed by existing work is limited, only considering object information from adjacent frames or video clips, leading to insufficient utilization of contextual information. To address this issue, we propose MambaLCT, which constructs and utilizes target variation cues from the first frame to the current frame for robust tracking. First, a novel unidirectional Context Mamba module is designed to scan frame features along the temporal dimension, gathering target change cues throughout the entire sequence. Specifically, target-related information in frame features is compressed into a hidden state space through selective scanning mechanism. The target information across the entire video is continuously aggregated into target variation cues. Next, we inject the target change cues into the attention mechanism, providing temporal information for modeling the relationship between the template and search frames. The advantage of MambaLCT is its ability to continuously extend the length of the context, capturing complete target change cues, which enhances the stability and robustness of the tracker. Extensive experiments show that long-term context information enhances the model’s ability to perceive targets in complex scenarios. MambaLCT achieves new SOTA performance on six benchmarks while maintaining real-time running speeds. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stream Concept-cognitive Computing System for Streaming data Learning

TechRxiv

引用

TechRxiv 2023年

作者： Mi, Yunlong Liu, Wenqi Shi, Yong The Big Data and Intelligent Decision Making Research Center Central South University Changsha410083 China The Data Science Research Center Kunming University of Science and Technology Kunming650500 China The Faculty of Science Kunming University of Science and Technology Kunming650500 China The School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China The Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China

People can often acquire knowledge dynamically and rapidly from different types of data, yet existing incremental learning algorithms are still computationally time consuming and most of stream learning methods are mainly designed for streaming data while ignoring other types of data. Hence, this paper proposes a novel dynamic concept learning (CL) algorithm by imitating human cognitive learning processes from the perspective of brain logical cognition, which is named stream concept-cognitive computing system (streamC3S). For streamC3S, it mainly consists of three aspects: the concept space, CL process, and model update process. Moreover, considering the concept drift frequently occurs in the streaming data over time, an extended version of streamC3S (namely, streamC3SE) is also proposed in this work. Specifically, we first show the related theories for streamC3S and streamC3SE on the basis of the concept space. Then an overall framework and its corresponding algorithm are shown. Finally, experimental results on various types of datasets, including the standard machine learning datasets, streaming datasets, image datasets, and two traffic data streams, validate the effectiveness of our streamC3S and streamC3SE compared to the state-of-the-art incremental learning and stream learning algorithms. © 2023, CC BY.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Structure Aware Loss for Deep Unsupervised Industrial Image Registration

Structure Aware Loss for Deep Unsupervised Industrial Image ...

引用

IEEE International Conference on data mining Workshops (ICDM Workshops)

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

ISBN: (数字)9798331530631

ISBN: (纸本)9798331530648

Image registration is extensively utilized in industrial applications. However, specific challenges inherent to these environments—such as low texture, significant displacement, and poor lighting conditions—complicate the registration process. This paper introduces a structure-aware loss module tailored to the unique characteristics of industrial images. This module promotes the network’s focus on salient regions while emphasizing structural features. Additionally, it is designed as a plug-in component, facilitating integration with any loss function and homography estimation method. We develop an unsupervised registration network and create an industrial dataset to evaluate the module’s effectiveness. A series of experiments demonstrate that our structure-aware module significantly enhances registration performance.

关键词： Deep learning Image registration Conferences Lighting Estimation data mining

来源：评论

学校读者我要写书评

暂无评论

Adaptive Robust Multi-View Linex-Based Xgboost Model for Credit Risk Assessment

SSRN

引用

SSRN 2023年

作者： Tang, Jingjing Zhu, Guorui Li, Jiahui Tian, Yingjie School of Business Administration Faculty of Business Administration Southwestern University of Finance and Economics Chengdu611130 China Institute of Big Data Southwestern University of Finance and Economics Chengdu611130 China School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China

Credit risk assessment is crucial for financial institutions. The data-driven methods regard the credit risk assessment as the class-imbalanced binary classification task since the non-default samples greatly outnumber default samples. Ensemble learning offers more advantages over traditional single classifier for credit risk assessment. Besides, the credit data can be extracted from multiple sources, such as personal credit data from financial institutions, personal tax payment data from government departments, telecommunications overdue data from public utilities, etc. They are typical multi-view data. How to fully exploit such multi-view and class-imbalanced data is the main challenge for the improvement of the credit risk assessment. This study proposes a cost-sensitive multi-view ensemble learning model called CSMEL. It firstly adapts the loss of XGBoost with the asymmetric LINEX loss function to construct the cost-sensitive base classifier, and then designs a multi-view ensemble learning framework for the combination of base classifiers. The asymmetry of Linex loss contributes to not only assign different weights to the misclassification errors from the non-default and default classes, but also make the base classifiers robust to noises. Extensive experiments on the Corel datasets and Credit risk datasets validate the effectiveness of the CSMEL model. © 2023, The Authors. All rights reserved.

关键词： Public utilities

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：