检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Qiu, Xiangfei Li, Xiuwen Pang, Ruiyang Pan, Zhicheng Wu, Xingjian Yang, Liu Hu, Jilin Shu, Yang Lu, Xuesong Yang, Chengcheng Guo, Chenjuan Zhou, Aoying Jensen, Christian S. Yang, Bin School of Data Science and Engineering East China Normal University Shanghai China Department of Computer Science Aalborg University Aalborg Denmark

Time series forecasting has important applications across diverse domains. EasyTime, the system we demonstrate, facilitates easy use of time-series forecasting methods by researchers and practitioners alike. First, EasyTime enables one-click evaluation, enabling researchers to evaluate new forecasting methods using the suite of diverse time series datasets collected in the preexisting time series forecasting benchmark (TFB). This is achieved by leveraging TFB's flexible and consistent evaluation pipeline. Second, when practitioners must perform forecasting on a new dataset, a nontrivial first step is often to find an appropriate forecasting method. EasyTime provides an Automated Ensemble module that combines the promising forecasting methods to yield superior forecasting accuracy compared to individual methods. Third, EasyTime offers a natural language Q&A module leveraging large language models. Given a question like "Which method is best for long term forecasting on time series with strong seasonality?", EasyTime converts the question into SQL queries on the database of results obtained by TFB and then returns an answer in natural language and charts. By demonstrating EasyTime, we intend to show how it is possible to simplify the use of time-series forecasting and to offer better support for the development of new generations of time series forecasting methods. © 2024, CC BY-NC-ND.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Aspect category and sentiment polarity detection using a permutation language-based transformer model

引用

Procedia computer science 2025年 258卷 4179-4189页

作者： Ashok Kumar Jayaraman Tina Ester Trueman Gayathri Ananthakrishnan Abirami Murugappan Erik Cambria Manikandan G Satanik Mitra HCLTech Engineering and R&D Services Chennai Tamil Nadu India Department of Computer Science University of the People California USA School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India Department of Information Science and Technology Anna University Chennai India College of Computing and Data Science Nanyang Technological University Nanyang Singapore School of Computer Science and Engineering Vellore Institute of Technology Vellore India Department of Management BITS Pilani India

Aspect-based sentiment analysis (ABSA) performs fine-grained analysis on text to determine a specific aspect category and a sentiment polarity. Recently, machine learning models have played a key role in ABSA tasks. In particular, transformer-based pre-trained models have achieved promising results in natural language processing tasks. Therefore, we propose a permutation based XLNet fine-tuning model for aspect category detection and sentiment polarity detection. Our model learns bidirectional contexts via positional encoding and factorization order. We evaluate the proposed permutation language model on three ABSA datasets, namely, SentiHood, SemEval 2015, and SemEval 2016. Specifically, we studied the ABSA tasks in a constrained system with a multi-class environment. Our result indicates that the proposed permutation language model achieves a better result.

关键词： Aspect-based sentiment analysis permutation language model deep learning transformers multiclass classification

来源：评论

学校读者我要写书评

暂无评论

Towards Robust Token Embeddings for Extractive Question Answering 1

引用

24th International Conference on Web Information Systems Engineering, WISE 2023

作者： Yao, Xun Ma, Junlong Hu, Xinrong Yang, Jie Guo, Yi Liu, Junping School of Computer Science and Artificial Intelligence Wuhan Textile University Wuhan China School of Computing and Information Technology University of Wollongong Wollongong Australia School of Computer Data and Mathematical Sciences Western Sydney University Penrith Australia

ISBN: (数字)9789819972548

ISBN: (纸本)9789819972531

Extractive Question Answering (EQA) tasks have gained intensive attention in recent years, while Pre-trained Language Models (PLMs) have been widely adopted for encoding purposes. Yet, PLMs typically take as initial input token embeddings and rely on attention mechanisms to extract contextual representations. In this paper, a simple yet comprehensive framework, termed perturbation for alignment (PFA), is proposed to investigate variations towards token embeddings. A robust encoder is further formed being tolerant against the embedding variation and hence beneficial to subsequent EQA tasks. Specifically, PFA consists of two general modules, including the embedding perturbation (a transformation to produce embedding variations) and the semantic alignment (to ensure the representation similarity from original and perturbed embeddings). Furthermore, the framework is flexible to allow several alignment strategies with different interpretations. Our framework is evaluated on four highly-competitive EQA benchmarks, and PFA consistently improves state-of-the-art models. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

QS-Craft: Learning to Quantize, Scrabble and Craft for Conditional Human Motion Animation 16th

QS-Craft: Learning to Quantize, Scrabble and Craft for Co...

引用

16th Asian Conference on computer Vision, ACCV 2022

作者： Hong, Yuxin Qian, Xuelin Luo, Simian Guo, Guodong Xue, Xiangyang Fu, Yanwei School of Data Science and MOE Frontiers Center for Brain Science Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai China School of Computer Science Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai China Department of CSEE West Virginia University Morgantown United States

ISBN: (纸本)9783031263507

This paper studies the task of conditional Human Motion Animation (cHMA). Given a source image and a driving video, the model should animate the new frame sequence, in which the person in the source image should perform a similar motion as the pose sequence from the driving video. Despite the success of Generative Adversarial Network (GANs) methods in image and video synthesis, it is still very challenging to conduct cHMA due to the difficulty in efficiently utilizing the conditional guided information such as images or poses, and generating images of good visual quality. To this end, this paper proposes a novel model of learning to Quantize, Scrabble, and Craft (QS-Craft) for conditional human motion animation. The key novelties come from the newly introduced three key steps: quantize, scrabble and craft. Particularly, our QS-Craft employs transformer in its structure to utilize the attention architectures. The guided information is represented as a pose coordinate sequence extracted from the driving videos. Extensive experiments on human motion datasets validate the efficacy of our model. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

A Discrete-Time Collaborative Neurodynamic Approach to Distributed Global Optimization

A Discrete-Time Collaborative Neurodynamic Approach to Distr...

引用

International Conference on Intelligent Control and Information Processing (ICICIP)

作者： Haoen Huang Zhigang Zeng Jun Wang School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Department of Computer Science & Department of Data Science City University of Hong Kong Kowloon Hong Kong

ISBN: (数字)9798331516147

ISBN: (纸本)9798331516154

In this paper, a discrete-time projection neural network with an adaptive step size (DPNN) is proposed for distributed global optimization. The DPNN is proven to be convergent to a Karush-Kuhn-Tucker point. Several DPNNs are utilized in a collaborative neurodynamic framework for solving distributed global optimization problem. The efficacy of the collaborative neurodynamic approach with DPNNs is demonstrated through simulation results.

关键词： Neurodynamics Adaptation models Adaptive systems Simulation Optimization models Neural networks Collaboration Information processing Optimization Intelligent control

来源：评论

学校读者我要写书评

暂无评论

IMGTP: A Unified Framework for Improving and Measuring the Generalizability of Trajectory Prediction Models

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第10期9卷 1-15页

作者： Ye, Luyao Zhou, Zikang Wang, Jianping Li, Yung-Hui Jan, Nien-Yi Lin, Yi-Rong Lin, Yen-Cheng National Engineering Research Center of Educational Big Data and the Faculty of Artificial Intelligence in Education Central China Normal University China Department of Computer Science City University of Hong Kong and City University of Hong Kong Shenzhen Research Institute China AI Research Center of Hon Hai Research Institute China

Accurately predicting nearby agents' future trajectories is fundamental for ensuring the safety and efficiency of autonomous driving. However, existing learning-based trajectory prediction models struggle with poor generalization to out-of-distribution (OOD) scenes, potentially leading to failed predictions in real-world applications. To tackle this challenge, we introduce IMGTP, a unified framework for systematically evaluating, improving, and measuring the generalization performance of trajectory prediction models in OOD scenes. IMGTP consists of three primary components: the Argoverse-Shift dataset, the FrenÃ©t+ strategy, and an approach for OOD measurement. First, the Argoverse-Shift is a cross-domain dataset that highlights the significant differences in data distributions across domains, serving as a testing platform for models' generalization ability. Second, the FrenÃ©t+ strategy leverages map centerlines and the FrenÃ©t Frame to enhance the generalizability of baseline models by mitigating the domain gap resulting from road geometry variations. Third, we provide a comprehensive evaluation methodology for OOD measurement, quantifying the range of data that can be effectively handled by prediction models. This measurement approach employs the accuracy rate of the correctly predicted samples and their corresponding mean distance as well as standard deviation to the training set center as indicators of the model's generalization ability. The mean distance also serves as a valid criterion for OOD detection and uncertainty quantification. Experimental results demonstrate that our IMGTP framework enhances the generalization capability of mainstream trajectory prediction models by substantially improving their prediction performance in unseen domains. This advancement contributes to developing more robust and safer prediction models for autonomous driving in the real world. The code can be found at https://***/XIAOYEJIAYOU/Frenet-Strategy. IEEE

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Nonstationary Network Traffic Prediction With RevIN-based LSTM 23

Nonstationary Network Traffic Prediction With RevIN-based LS...

引用

Proceedings of the 2023 13th International Conference on Communication and Network Security

作者： Zeyi Liu Xiaodong Guo Yinan Yao Yuzhong Chen Xin Yang Jiayin Li College of Computer and Data Science Fuzhou University China College of Computer and Cyber security Fujian Normal University China

ISBN: (纸本)9798400707964

With the continuous development of the Internet, the need to optimize the network structure and ensure its stable operation has become a pressing issue in the network. Consequently, accurate and real-time network traffic prediction models play a crucial role in network optimization. Although there are various series of data prediction models, they still perform poorly in real-time network traffic prediction because network traffic is often non-stationary. This paper aims to use deep learning models for network traffic prediction, especially for non-stationary network traffic data. Using a combination of the Reversible instance normalization (RevIN) method and the Long Short Term Memory (LSTM) model and adding a Self-Attention layer can enhance the model’s ability to capture long-term features. Also, an offset in the distribution between the lookback window and the horizon window is considered in the model. The experimental results show that the model outperforms previous research methods on the task of non-stationary network traffic prediction, which provides an important reference for optimizing the network.

关键词： Attention mechanism LSTM RevIN network traffic prediction nonstationary network traffic data

来源：评论

学校读者我要写书评

暂无评论

Implicitly Guided Design with PropEn: Match your data to Follow the Gradient

arXiv

引用

arXiv 2024年

作者： Tagasovska, Nataša Gligorijević, Vladimir Cho, Kyunghyun Loukas, Andreas Prescient/MLDD Genentech Research and Early Development Department of Computer Science Center for Data Science New York University United States

Across scientific domains, generating new models or optimizing existing ones while meeting specific criteria is crucial. Traditional machine learning frameworks for guided design use a generative model and a surrogate model (discriminator), requiring large datasets. However, real-world scientific applications often have limited data and complex landscapes, making data-hungry models inefficient or impractical. We propose a new framework, PropEn, inspired by "matching", which enables implicit guidance without training a discriminator. By matching each sample with a similar one that has a better property value, we create a larger training dataset that inherently indicates the direction of improvement. Matching, combined with an encoder-decoder architecture, forms a domain-agnostic generative framework for property enhancement. We show that training with a matched dataset approximates the gradient of the property of interest while remaining within the data distribution, allowing efficient design optimization. Extensive evaluations in toy problems and scientific applications, such as therapeutic protein design and airfoil optimization, demonstrate PropEn's advantages over common baselines. Notably, the protein design results are validated with wet lab experiments, confirming the competitiveness and effectiveness of our approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

UNDERSTANDING AND MITIGATING MISCALIBRATION IN PROMPT TUNING FOR VISION-LANGUAGE MODELS

arXiv

引用

arXiv 2024年

作者： Wang, Shuoyuan Li, Yixuan Wei, Hongxin Department of Statistics and Data Science Southern University of Science and Technology China Department of Computer Sciences University of Wisconsin-Madison United States

Confidence calibration is critical for the safe deployment of machine learning models in the real world. However, such issue in vision-language models like CLIP, particularly after fine-tuning, has not been fully addressed. In this work, we demonstrate that existing prompt tuning methods usually lead to a trade-off of calibration between base and new classes: the cross-entropy loss in CoOp causes overconfidence in new classes by increasing textual label divergence, whereas the regularization of KgCoOp maintains the confidence level but results in underconfidence in base classes due to the improved accuracy. Inspired by the observations, we introduce Dynamic Outlier Regularization (DOR) to ensure the confidence calibration on both base and new classes after fine-tuning. In particular, we propose to minimize the feature deviation of novel textual labels (instead of base classes) sampled from a large vocabulary. In effect, DOR prevents the increase in textual divergence for new labels while easing restrictions on base classes. Extensive experiments demonstrate that DOR can enhance the calibration performance of current fine-tuning methods on base and new classes. © 2024, CC0.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Examining Digital Forensic Evidence for Android Applications 23

Examining Digital Forensic Evidence for Android Applications

引用

23rd International Arab Conference on Information Technology, ACIT 2022

作者： Al-Mousa, Mohammad Rasmi Al-Zaqebah, Qutaiba Saeb Al-Sherideh, Ala'A Al-Ghanim, Mohammed Samara, Ghassan Al-Matarneh, Sattam Asassfeh, Mahmoud Zarqa University Department of Cyber Security Zarqa Jordan Zarqa University Department of Computer Science Zarqa Jordan Zarqa University Department of Data Science and Artificial Intelligence Jordan

ISBN: (纸本)9798350320244

The examination of digital forensic evidence is a science highlighting the main areas of progress in forensic science. Various social media sites (SNS) providing e-mail services, messages, pictures, and videos have brought about a huge explosion in development. In recent times, Digital Forensics has expanded to be used in all institutions and companies, especially financial companies, pharmaceutical companies, and investment companies. With this electronic development, criminal activities have dramatically increased to obtain and steal data for personal or international interests or the so-called data theft. Therefore, the biggest challenge lies in protecting this information from theft and searching for digital forensic evidence so that the digital evidence is correct and sound from a forensic point of view. Against this, this paper provides a detailed review of the most important Android applications in digital forensics to attain, retrieve, and compare information altogether. © 2022 IEEE.

关键词： Digital forensics

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：