检索结果-内蒙古大学图书馆

Non-salient region erasure for time series augmentation

Frontiers of Computer science 2022年第6期16卷 203-205页

作者： Pin LIU Xiaohui GUO Bin SHI Rui WANG Tianyu WO Xudong LIU State Key Lab of Software Development Environment(SKLSDE) Beihang UniversityBeijing100191China Beijing Advanced Innovation Center for Big Data and Brain Computing(BDBC) Beijing100191China Hangzhou Innovation Institute Beihang UniversityHangzhou310052China School of Computer Science and Technology Xi’an Jiaotong UniversityXi’an710049China

1 Introduction Time seriesaugmentationis an essential approachto solvethe overfitting problem on the time series classification(TSC)task[1,2].Although existing approaches perform better in mitigating this problem,none of them focus on protecting saliency regions on time *** key informative shapelets contained in these regions are the core basis for distinguishing categories(e.g.,upward spikes in ECG and high amplitude in Sensor).

关键词： Sensor series series

来源：评论

学校读者我要写书评

暂无评论

Research on the Trust Mechanism of Community Social Enterprises Based on Non-Linear Regression Model 21

Research on the Trust Mechanism of Community Social Enterpri...

引用

21st International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2023

作者： Tong, He Cui, Qing-Zhe Xu, Wei Jin, Ding-Ge Li, Meng-Ying Xu, Ting-Ting Xu, Li-Xiang Tang, Yuan-Yan Chinese people's Liberation Army Aviation School Department of Basic Beijing101123 China School of Artificial Intelligence and Big Data Hefei University Hefei230601 China School of Public Afairs University of Science and Technology of China Hefei230026 China Party School of Lu'an Municipal Committee of the Communist Party of China Economics Teaching and Research Office China Zhuhai UM Science and Technology Research Institute FST University of Macau Macau China

ISBN: (纸本)9798350303810

In recent years, social enterprises have gradually emerged as a major force in community governance. In order for social enterprises to better participate in community governance, this paper examines the trust mechanism between social enterprises and community governance, and offers suggestions for social enterprises in community governance. Firstly, this paper takes social trust as the object of study, divides it into ordinary trust and spe-cial trust, community governance effect as the dependent variable, selects intermediate variables to construct a non-linear regression model, and combines the correlation coefficient analysis to derive the mechanism of building trust relationship between social enterprises and community governance. Finally, there are sound suggestions for community governance aspects. © 2023 IEEE.

关键词： Correlation coefficient Non-linear regression model Social Enterprise Trust in Society

来源：评论

学校读者我要写书评

暂无评论

Bridging Knowledge Gap Between Image Inpainting and Large-Area Visible Watermark Removal 39

Bridging Knowledge Gap Between Image Inpainting and Large-Ar...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Leng, Yicheng Fang, Chaowei Chen, Junye Fang, Yixiang Li, Sheng Li, Guanbin School of Artificial Intelligence Xidian University Xi’an China School of Data Science The Chinese University of HongKong Shenzhen China School of Computer Science and Engineering Research Institute of Sun Yat-sen University in Shenzhen Sun Yat-sen University Guangzhou China Afirstsoft Shenzhen China GuangDong Province Key Laboratory of Information Security Technology China

ISBN: (纸本)157735897X

Visible watermark removal which involves watermark cleaning and background content restoration is pivotal to evaluate the resilience of watermarks. Existing deep neural network (DNN)-based models still struggle with large-area watermarks and are overly dependent on the quality of watermark mask prediction. To overcome these challenges, we introduce a novel feature adapting framework that leverages the representation modeling capacity of a pre-trained image inpainting model. Our approach bridges the knowledge gap between image inpainting and watermark removal by fusing information of the residual background content beneath watermarks into the inpainting backbone model. We establish a dual-branch system to capture and embed features from the residual background content, which are merged into intermediate features of the inpainting backbone model via gated feature fusion modules. Moreover, for relieving the dependence on high-quality watermark masks, we introduce a new training paradigm by utilizing coarse watermark masks to guide the inference process. This contributes to a visible image removal model which is insensitive to the quality of watermark mask during testing. Extensive experiments on both a large-scale synthesized dataset and a real-world dataset demonstrate that our approach significantly outperforms existing state-of-the-art methods. The source code is available in the supplementary materials. © 2025, Association for the Advancement of Artificial Intelligence (***). 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

Time Series analysis with ARIMA for historical stock data and future projections

引用

Soft Computing 2024年第21期28卷 12531-12542页

作者： Dar, Amir Ahmad Jain, Akshat Malhotra, Mehak Farooqi, Ataur Rahman Albalawi, Olayan Khan, Mohammad Shahfaraz Hiba School of Chemical Sciences and Physical Sciences Lovely Professional University Punjab Phagwara India Statistics and Data Analytics Lovely Professional University Punjab Phagwara India CEBA University of Technology and Applied Sciences Nizwa Oman Department of Statistics Faculty of Science University of Tabuk Tabuk Saudi Arabia College of Economics and Business Administration University of Technology and Applied Sciences Salalah Oman

Forecasting stock prices is difficult because of the many unknowns and diverse factors that affect the financial market. Using time series data, the study attempts to assess how well the ARIMA (Auto Regressive Integrated Moving Average) model predicts the stock prices of Maersk, a significant participant in the global shipping industry. The research methodology is based on the Box-Jenkins approach, which includes model identification, estimation, and diagnostic checking to ensure reliable predictions. To ensure reliable time series forecasting, the analysis begins with the Augmented Dickey-Fuller (ADF) test, which checks for stationarity. The Akaike Information Criterion (AIC), which measures model complexity and predictive accuracy equally, serves as a guide for selecting models. The ARIMA model’s performance is assessed by comparing predicted stock prices with actual observed values. The findings show the ARIMA model’s usefulness in financial time series analysis by showing that it can accurately predict Maersk’s stock prices. The model’s suitability for stock price forecasting is confirmed by a variety of statistical metrics that validate its predictive ability. The usefulness of ARIMA models in financial forecasting is highlighted by this study, which provides insightful information to help analysts and investors make wise decisions. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Comparative research on multi-source heterogeneous data fusion technologies

引用

Procedia Computer science 2024年 242卷 1089-1095页

作者： Wen Long Jing Gao Man Guo School of Economics and Management University of Chinese Academy of Sciences Beijing 100090 China Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining & Knowledge Management Chinese Academy of Sciences Beijing 100190 China

Both structured market data and unstructured financial news data can significantly affect stock price fluctuations. Therefore, relying only on a single data source for stock price trend prediction may produce information bias. This article combines these two types of heterogeneous data and systematically compares the effectiveness of different data fusion technologies to establish the optimal data integration strategy, thereby improving the accuracy of stock price prediction. Specifically, this paper innovatively proposes a stock price trend prediction model named MVL-SVM. The model successfully combines multi-perspective learning with support vector machine, and realizes the effective fusion of stock market data and financial news data. It is worth mentioning that the prediction accuracy of MVL-SVM model using direct fusion method is more than 30% higher than that of index modeling method, which indicates that direct fusion method can fully learn effective information from multiple information sources, thus significantly improving the prediction effect.

关键词： Multi-view Learning MVL-SVM Market data Financial news data Heterogeneous data fusion

来源：评论

学校读者我要写书评

暂无评论

UVTM: Universal Vehicle Trajectory Modeling with ST Feature Domain Generation

引用

IEEE Transactions on Knowledge and data Engineering 2025年

作者： Lin, Yan Hu, Jilin Guo, Shengnan Yang, Bin Jensen, Christian S. Lin, Youfang Wan, Huaiyu Aalborg University Department of Computer Science Aalborg9220 Denmark East China Normal University School of Data Science and Engineering Shanghai200050 China Beijing Jiaotong University Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence School of Computer Science and Technology Beijing100044 China

Vehicle movement is frequently captured in the form of GPS trajectories, i.e., sequences of timestamped GPS locations. Such data is widely used for various tasks such as travel-time estimation, trajectory recovery, and trajectory prediction. A universal vehicle trajectory model could be applied to different tasks, removing the need to maintain multiple specialized models, thereby reducing computational and storage costs. However, creating such a model is challenging when the integrity of trajectory features is compromised, i.e., in scenarios where only partial features are available or the trajectories are sparse. To address these challenges, we propose the Universal Vehicle Trajectory Model (UVTM), which can effectively adapt to different tasks without excessive retraining. UVTM incorporates two specialized designs. First, it divides trajectory features into three distinct domains. Each domain can be masked and generated independently to accommodate tasks with only partially available features. Second, UVTM is pre-trained by reconstructing dense, feature-complete trajectories from sparse, feature-incomplete counterparts, enabling strong performance even when the integrity of trajectory features is compromised. Experiments involving four representative trajectory-related tasks on three real-world vehicle trajectory datasets provide insight into the performance of UVTM and offer evidence that it is capable of meeting its objectives. © 1989-2012 IEEE.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Dynamic Pricing Strategy with Pay-Per-Chapter Mode for Online Publisher with Case Study Ofcol

SSRN

引用

SSRN 2024年

作者： Fang, Lang Pan, Zhendong Tang, Jiafu School of Management Science & Engineering Liaoning Key Laboratory of Big Data Management and Optimization Decision Dongbei University of Finance and Economics Dalian China

We consider how to make dynamic pricing decision for Chinese Online (COL) at T time-points, an online publisher that allow authors to sell their ongoing book projects. Instead of paying for a book, readers pay for each chapter (pay-per-chapter mode) of the ongoing book project. This mode allows readers to pay for as many chapters as they want without taking the risk that the releasing of new chapters might be delayed or stopped. Despite of the dynamics of chapter-by-chapter released of COL products, the fixed pricing strategy (FPS) does not make fully use of the reading data generated by releasing chapters of the ongoing book. We propose a learning-based dynamic pricing strategy (LDPS) that exploits the newly information to maximize cumulative revenue for the publisher. The LDPS captures the ever changing features of readers. It employs the Thompson sampling method to balance the exploration of the readers’ features with the exploitation of publisher’s knowledge to determine optimal price. Taking COL as a case study and implementing our policies in the context of the aforementioned real-life data set, we show that LDPS outperform several classical strategies such as Greedy, Prior-Free TS and Prior-Given TS, and average revenue of LDPS is increased by 0.5% average per time-point compared to the publisher’s historical decisions. We also provide some management implications for the COL publisher by analyzing the pricing range of different genres of books and choice of the exploration threshold parameter. © 2024, The Authors. All rights reserved.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Energy Requirement and Availability Analysis in the Indian Subcontinent using Machine Learning 9

Energy Requirement and Availability Analysis in the Indian S...

引用

9th IEEE International Conference for Convergence in technology, I2CT 2024

作者： Annadate, Prutha Annadate, Mrunal Dr. Vishwanath Karad Mit World Peace University School of Computer Engineering And Technology - Artificial Intelligence And Data Science Pune India Dr. Vishwanath Karad Mit World Peace University School of Electronics And Communication Engineering Pune India

ISBN: (纸本)9798350394474

Efficient energy data analysis and then prediction can be especially beneficial in the Indian Subcontinent with its ever-growing need and industrial expansion. The authors developed and compared three different machine learning (ML) models namely, Linear Regression, Decision Tree Regression and Random Forest Regressor for energy requirement against energy availability analysis restricted to the mentioned region. The models achieved an R2 value of 99.76%, 99.58% and 99.72% respectively. Observations regarding the results obtained were discussed along with a review of related works. Finally, the authors provided some pointers for future research. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging in-the-wild data for Effective Self-supervised Pretraining in Speaker Recognition

Leveraging in-the-wild Data for Effective Self-supervised Pr...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shuai Wang Qibing Bai Qi Liu Jianwei Yu Zhengyang Chen Bing Han Yanmin Qian Haizhou Li Shenzhen Research Institute of Big Data Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen (CUHK-Shenzhen) China Tencent Shenzhen China Shanghai Jiao Tong University Shanghai China

Current speaker recognition systems primarily rely on supervised approaches, constrained by the scale of labeled datasets. To boost the system performance, researchers leverage large pretrained models such as WavLM to transfer learned high-level features to the downstream speaker recognition task. However, this approach introduces extra parameters as the pretrained model remains in the inference stage. Another group of researchers directly apply self-supervised methods such as DINO to speaker embedding learning, yet they have not explored its potential on large-scale in-the-wild datasets. In this paper, we present the effectiveness of DINO training on the large-scale WenetSpeech dataset and its transferability in enhancing the supervised system performance on the CNCeleb dataset. Additionally, we introduce a confidence-based data filtering algorithm to remove unreliable data from the pretraining dataset, leading to better performance with less training data. The associated pretrained models, confidence files, pretraining and finetuning scripts will be made available in the Wespeaker toolkit.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Boosting transferability and discriminability for time series domain adaptation 24

Boosting transferability and discriminability for time serie...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Mingyang Liu Xinyang Chen Yang Shu Xiucheng Li Weili Guan Liqiang Nie School of Computer Science and Technology Harbin Institute of Technology (Shenzhen) School of Data Science and Engineering East China Normal University School of Electronics and Information Engineering Harbin Institute of Technology (Shenzhen)

ISBN: (纸本)9798331314385

Unsupervised domain adaptation excels in transferring knowledge from a labeled source domain to an unlabeled target domain, playing a critical role in time series applications. Existing time series domain adaptation methods either ignore frequency features or treat temporal and frequency features equally, which makes it challenging to fully exploit the advantages of both types of features. In this paper, we delve into transferability and discriminability, two crucial properties in transferable representation learning. It's insightful to note that frequency features are more discriminative within a specific domain, while temporal features show better transferability across domains. Based on the findings, we propose Adversarial CO-learning Networks (ACON), to enhance transferable representation learning through a collaborative learning manner in three aspects: (1) Considering the multi-periodicity in time series, multi-period frequency feature learning is proposed to enhance the discriminability of frequency features; (2) Temporal-frequency domain mutual learning is proposed to enhance the discriminability of temporal features in the source domain and improve the transferability of frequency features in the target domain; (3) Domain adversarial learning is conducted in the correlation subspaces of temporal-frequency features instead of original feature spaces to further enhance the transferability of both features. Extensive experiments conducted on a wide range of time series datasets and five common applications demonstrate the state-of-the-art performance of ACON. Code is available at https://***/mingyangliu1024/ACON.

关键词：

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：