检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Binyan Ren, Ao Zhang, Zihao Duan, Moming Liu, Duo Tan, Yujuan Zhong, Kan College of Computer Science Chongqing University Chongqing China School of Big Data Software & Engineering Chongqing University Chongqing China Institute of Data Science National University of Singapore Singapore

ISBN: (纸本)9798350368741

With the rapid development of social media, sentiment analysis from multimodal posts has garnered significant attention in recent years. However, the substantial size of these models impedes their deployment on resource-constrained embedded devices. Although pruning has been extensively studied to reduce the size of unimodal models, specific challenges remain for Multimodal Sentiment Analysis (MSA) models. First, existing techniques prune fixed original models into sparse models, while our findings indicate that different model architectures of identical size yield varying performance outcomes. Second, prior studies fail to explore the unique characteristics of MSA models, resulting in suboptimal pruning performance. To address these challenges, we propose MPNAS, a unified pruning framework via Neural Architecture Search (NAS) for MSA models. Specifically, we formulate pruning as a NAS problem and analyze MSA model characteristics to guide the subnet search. We conduct an initial coarse-grained NAS on the original model, expanding the search space slightly to identify suitable subnets that enhance pruning rates and accuracy. Subsequently, we refine coarse-grained subnets in a fine-grained NAS stage, where MSA model characteristics guide the search process. Extensive experiments on three representative datasets demonstrate the superiority of our approach over existing methods. © 2025 IEEE.

关键词： Multimodal Compression NAS

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Deep Learning Approach for Typhoon Track Forecast by Fusing CNN and Transformer Structures 4

A Multimodal Deep Learning Approach for Typhoon Track Foreca...

引用

4th International Conference on computer Vision, Image and Deep Learning, CVIDL 2023

作者： Zhan, Ruijie Lu, Jiadong Jiang, Yuchao Li, Tongfei Zhong, Guohao Lv, Wei City University of Macau Falcuty of Data Science 999078 China School of Aliyun Big Data Applications Zhuhai College of Science and Technology Zhuhai519041 China School of Computer Science Zhuhai College of Science and Technology Zhuhai519041 China

ISBN: (纸本)9798350326444

The prediction of typhoon trajectory is essential to protect people and property. However, traditional methods of typhoon track prediction are difficult to guarantee the prediction efficiency and accuracy when dealing with a large amount of complex data. With the improvement of computer computing power and the development of deep learning technology, deep neural networks are gradually applied to the field of meteorology. In this paper, we describe a typhoon trajectory prediction model named TyT (Typhoon technology with Transformer), which effectively uses large-scale multimodal historical data and advanced deep learning techniques to achieve typhoon trajectory forecasting. With the above design, Our TyT can make full use of the implicit correlation of multimodal data to realize the advantages that unimodal data-based methods do not have. Meanwhile, the structure of Transformer enables to establish long-range dependencies by attention mechanism and position encoding. Experiments on historical typhoon track data in the northwest Pacific Ocean show that our TyT has a significant improvement in accuracy compared to previous typhoon track prediction methods. Finally, four different typhoons are randomly selected to plot their tracks to visually demonstrate the prediction performance of our TyT. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Sustainable Diffusion-Based Incentive Mechanism for Generative AI-Driven Digital Twins in Industrial Cyber-Physical Systems

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 139-149页

作者： Wen, Jinbo Kang, Jiawen Niyato, Dusit Zhang, Yang Mao, Shiwen Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing210016 China Guangdong University of Technology School of Automation Guangzhou510006 China Nanyang Technological University College of Computing and Data Science Singapore639798 Singapore Auburn University Department of Electrical and Computer Engineering AuburnAL36849 United States

Industrial Cyber-Physical Systems (ICPSs) are an integral component of modern manufacturing and industries. By digitizing data throughout product life cycles, Digital Twins (DTs) in ICPSs enable a shift from current industrial infrastructures to intelligent and adaptive infrastructures. Thanks to data process capability, Generative Artificial Intelligence (GenAI) can drive the construction and update of DTs to improve predictive accuracy and prepare for diverse smart manufacturing. However, mechanisms that leverage Industrial Internet of Things (IIoT) devices to share sensing data for DT construction are susceptible to adverse selection problems. In this paper, we first develop a GenAI-driven DT architecture in ICPSs. To address the adverse selection problem caused by information asymmetry, we propose a contract theory model and develop a sustainable diffusion-based soft actor-critic algorithm to identify the optimal feasible contract. Specifically, we leverage dynamic structured pruning techniques to reduce parameter numbers of actor networks, allowing sustainability and efficient implementation of the proposed algorithm. Numerical results demonstrate the effectiveness of the proposed scheme and the algorithm, enabling efficient DT construction and updates to monitor and manage ICPSs. © 2023 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

A Method of Selecting Negative Examples from Clinical EEG by Combining Ensemble Learning and Uncertainty Estimation 17

A Method of Selecting Negative Examples from Clinical EEG by...

引用

17th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2024

作者： Liu, Jianwen Han, Liyong Huang, Zexin Lin, Zhixiong Wang, Chenghua Huang, Zhihua College of Computer and Data Science Fuzhou University Fuzhou China Fujian Sanbo Funeng Brain Hospital Fuzhou China

ISBN: (纸本)9798331507398

Electroencephalogram (EEG) analysis is a critical tool for diagnosing various neurological disorders. Intelligent EEG models facilitate the analysis and diagnosis of these conditions. However, the development of such models relies on expert labeling of EEG signals. Due to limited time and resources, experts typically only label positive examples, leaving the selection of negative examples to be handled by algorithms. This paper proposes a novel method for selecting EEG negative samples by integrating ensemble learning with uncertainty estimation. The method employs a Stacking ensemble strategy, with AtcNet, USleep, and EEG Transformer as base learners, and Support Vector Machines (SVM) as meta-learners. By integrating two uncertainty metrics, the Variance Metric (VAR) and the Kullback-Leibler Divergence Metric (KL), this method selects high-quality EEG negative samples. Experimental results demonstrate that this approach significantly improves the model's performance. the quality of negative example samples selected by this method is better than that selected by any one of the models of AtcNet, USleep, and EEG Transformer alone. Compared to the baseline method, the proposed method enhances the macro-average F1 score by up to 5.67%. This study confirms the superiority of the proposed negative sample selection method and the effectiveness of the constructed dataset. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

ML-KFHE: Multi-label Ensemble Classification Algorithm Exploiting Sensor Fusion Properties of the Kalman Filter

引用

SN computer science 2023年第6期4卷 821页

作者： Pakrashi, Arjun Mac Namee, Brian School of Computer Science University College Dublin Dublin Ireland Insight Centre for Data Analytics Dublin Ireland

Despite the success of ensemble classification methods in multi-class classification problems, ensemble methods based on approaches other than bagging have not been widely explored for multi-label classification problems. The Kalman filter-based Heuristic ensemble (KFHE) is an ensemble method that exploits the sensor fusion properties of the Kalman filter to combine several classifier models, and that has been shown to be very effective. This work proposes a multi-label version of KFHE, ML-KFHE, demonstrating the effectiveness of the KFHE method on multi-label datasets. Two variants are introduced based on the underlying component classifier algorithm, ML-KFHE-HOMER, and ML-KFHE-CC which uses HOMER and classifier chain (CC) as the underlying multi-label algorithms, respectively. ML-KFHE-HOMER and ML-KFHE-CC sequentially train multiple HOMER and CC multi-label classifiers and aggregate their outputs using the sensor fusion properties of the Kalman filter. Extensive experiments and detailed analysis were performed on thirteen multi-label datasets and eight other algorithms, which included state-of-the-art ensemble methods. The results show, for both versions, the ML-KFHE framework improves the predictive performance significantly with respect to bagged combinations of HOMER (named E-HOMER), also introduced in this paper, and bagged combination of CC, ensemble classifier chains (ECC), thus demonstrating the effectiveness of ML-KFHE. Also, the ML-KFHE-HOMER variant was found to perform consistently and significantly better than the compared multi-label methods including existing approaches based on ensembles. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Classifier fusion Ensembles Kalman filter Multi-label classification

来源：评论

学校读者我要写书评

暂无评论

A Privacy-Preserving E-Voting System Using Blockchain and Linkable Ring Signatures 1

A Privacy-Preserving E-Voting System Using Blockchain and Li...

引用

1st International Conference on Innovative and Intelligent Information Technologies, IC3IT 2024

作者： Berkani, Ahmed-Sami Moumen, Hamouma Benharzallah, Saber Achouri, Youssouf Kechadi, Mohand Tahar Lamie Laboratory University of Batna 2 Department of Computer Science Batna Algeria LaSTIC Laboratory University of Batna 2 Department of Computer Science Batna Algeria School of Computer Science University College Dublin Insight Centre for Data Analytics Belfield Ireland

ISBN: (纸本)9798331541064

In this work we propose a privacy-preserving, blockchain-enabled e-voting system that integrates Linkable Ring Signatures (LRS) to ensure a secure, scalable, and privacypreserving solution for modern e-voting, providing a framework for trusted and transparent electoral processes in the digital age. Our system ensures voter anonymity while preventing double voting through the use of a linkability tag, while blockchain technology is employed to provide an immutable and transparent ledger for vote recording. The InterPlanetary File System (IPFS) is utilized for decentralized and GDPR-compliant storage of public keys. Performance analysis shows scalability challenges for LRS in large elections, but the system remains efficient for small scale use. Future work will focus on optimizing scalability for larger deployments. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

RUP2S- YOLO: An Improved YOLOv8-Based Algorithm for Dense Pedestrian Detection 5

RUP2S- YOLO: An Improved YOLOv8-Based Algorithm for Dense Pe...

引用

5th International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2024

作者： Wang, Juanmin Huang, Kun Pi, Jianyong College of Computer Science and Technology Guizhou University State Key Laboratory of Public Big Data Guizhou Guiyang China

ISBN: (纸本)9798350385557

Dense pedestrian detection is a key research direction in the field of computer vision, which plays a significant role in large-scale crowded public spaces. It provides strong technical support for security assurance, traffic management, and behavioral analysis in public areas. To address the issue of missed detection of small-sized occluded pedestrians in dense scenarios, this paper proposes an improved detection algorithm based on YOLOv8, named RUP2S-YOLO. For the backbone network, the RFCBAM module is used to replace the convolution module to enhance the capability of capturing subtle features and better extract the characteristics of small-scale pedestrians;for the C2f module, the UKMS module is designed as a substitution aiming to improve the model's capacity to process information of different scales;for the detection head, the P2S module is introduced for the accurate positioning of small-scale targets. Experiments on dense pedestrian datasets show that the improved RUP2S-YOLO outperforms the original algorithm in terms of performance, achieving an AP50 of 82.8%, and an AP50:95 of 55.8%, which represents an increase of 2.2% and 2.8% respectively compared to the original algorithm. Meanwhile, in comparison with other leading pedestrian detection models, the improved YOLOv8 algorithm presented in this article also demonstrates competitive advantages. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Transformer-Based Video Colorization Method Fusing Local Self-attention and Bidirectional Optical Flow 10th

A Transformer-Based Video Colorization Method Fusing Local S...

引用

10th International Conference of Pioneering computer Scientists, Engineers and Educators, ICPCSEE 2024

作者： Yuan, Lin Duan, Xun Xiang, Lingjie Kong, Guangqian Wu, Yun State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China

ISBN: (纸本)9789819787456

Video colorization encounters two principal challenges: colorization quality and temporal flicker. Balancing colorization quality and temporal consistency is a significant challenge. To address the aforementioned issues, we employ the transformer model in the field of video colorization and introduce a pioneering video colorization method named VCTR. Initially, to guarantee the quality of video coloring, we employ a pretrained image coloring network to add color to the grayscale video frame. Next, the feature extraction module for VCTR is utilized to perform feature extraction and propagation on the color frames during the colorization process. Finally, the transformer module is designed to fully leverage local information via the local feature self-attention layer. Additionally, motion information from bidirectional optical flow is utilized to identify correlations across video frames for feature fusion, guaranteeing both the coloring effect and temporal consistency. The experimental results demonstrate that VCTR outperforms existing methods on two publicly available datasets, namely, DAVIS and Videvo. VCTR attains the top ranking in the long-series dataset, Videvo, based on the CTBI (Colorization and Temporal-Consistency Balance Index). This achievement underscores VCTR’s ability to strike a commendable balance between colorization quality and temporal consistency. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

SSDRec: Self-Augmented Sequence Denoising for Sequential Recommendation 40

SSDRec: Self-Augmented Sequence Denoising for Sequential Rec...

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Zhang, Chi Han, Qilong Chen, Rui Zhao, Xiangyu Tang, Peng Song, Hongtao College of Computer Science and Technology Harbin Engineering University China School of Data Science City University of Hong Kong Hong Kong School of Cyber Science and Technology Shandong University China

ISBN: (纸本)9798350317152

Traditional sequential recommendation methods assume that users' sequence data is clean enough to learn accurate sequence representations to reflect user preferences. In practice, users' sequences inevitably contain noise (e.g., accidental interactions), leading to incorrect reflections of user preferences. Consequently, some pioneer studies have explored modeling sequentiality and correlations in sequences to implicitly or explicitly reduce noise's influence. However, relying on only available intra-sequence information (i.e., sequentiality and correlations in a sequence) is insufficient and may result in over-denoising and under-denoising problems (OUPs), especially for short sequences. To improve reliability, we propose to augment sequences by inserting items before denoising. However, due to the data sparsity issue and computational costs, it is challenging to select proper items from the entire item universe to insert into proper positions in a target sequence. Motivated by the above observation, we propose a novel framework-Self-augmented Sequence Denoising for sequential Recommendation (SSDRec) with a three-stage learning paradigm to solve the above challenges. In the first stage, we empower SSDRec by a global relation encoder to learn multi-faceted inter-sequence relations in a data-driven manner. These relations serve as prior knowledge to guide subsequent stages. In the second stage, we devise a self-augmentation module to augment sequences to alleviate OUPs. Finally, we employ a hierarchical denoising module in the third stage to reduce the risk of false augmentations and pinpoint all noise in raw sequences. Extensive experiments on five real-world datasets demonstrate the superiority of SSDRec over state-of-the-art denoising methods and its flexible applications to mainstream sequential recommendation models. The source code is available online at https://***/zc-97/SSDRec. © 2024 IEEE.

关键词： User profile

来源：评论

学校读者我要写书评

暂无评论

Probabilistic time series forecasting with deep non-linear state space models

引用

CAAI Transactions on Intelligence Technology 2023年第1期8卷 3-13页

作者： Heming Du Shouguo Du Wen Li School of Computer Science College of Engineering and Computer ScienceAustralian National UniversityCanberraAustralian Capital TerritoryAustralia Shanghai Municipal Big Data Center ShanghaiChina Department of Economic Statistics School of Statistics and InformationShanghai University of International Business and EconomicsShanghaiChina

Probabilistic time series forecasting aims at estimating future probabilistic distributions based on given time series *** is a widespread challenge in various tasks,such as risk management and decision *** investigate temporal patterns in time series data and predict subsequent probabilities,the state space model(SSM)provides a general *** of SSM achieve considerable success in many fields,such as engineering and ***,since underlying processes in real-world scenarios are usually unknown and complicated,actual time series observations are always irregular and ***,it is very difficult to determinate an SSM for classical statistical *** this paper,a general time series forecasting framework,called Deep Nonlinear State Space Model(DNLSSM),is proposed to predict the probabilistic distribution based on estimated underlying unknown processes from historical time series *** fuse deep neural networks and statistical methods to iteratively estimate states and network parameters and thus exploit intricate temporal patterns of time series *** particular,the unscented Kalman filter(UKF)is adopted to calculate marginal likelihoods and update distributions recursively for non-linear *** that,a non-linear Joseph form covariance update is developed to ensure that calculated covariance matrices in UKF updates are symmetric and positive ***,the authors enhance the tolerance of UKF to round-off errors and manage to combine UKF and deep neural *** this manner,the DNLSSM effectively models non-linear correlations between observed time series data and underlying dynamic *** in both synthetic and real-world datasets demonstrate that the DNLSSM consistently improves the accuracy of probability forecasts compared to the baseline methods.

关键词： Artificial Intelligence machine learning time series

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：