检索结果-内蒙古大学图书馆

4th Asia-Pacific Artificial Intelligence and big data Forum, AIBDF 2024

作者： Zhao, Feng Fan, Wenxuan Han, Zhongwei Chen, Hongyu School of Computer Science and Technology Shandong Technology and Business University Shandong Yantai China Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Shandong Yantai China Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China Information Engineering College Yantai Institute of Technology Shandong Yantai China Shandong Technology and Business University Shandong Yantai China

ISBN: (纸本)9798400710865

Functional connectivity networks (FCNs), particularly those utilizing the phase lag index (PLI) method, have been instrumental in elucidating the pathological features of Major Depressive Disorder (MDD) by assessing the synchrony and lag of electroencephalogram (EEG) signal waveforms. Currently, the more prevalent methods are traditional FCNs that quantify phase synchronization as scalar values and dynamic FCNs (D-FCNs) that employ sliding window approaches to capture the instantaneous variations in functional connectivity. However, these two methods merely capture the low-level functional connections between paired regions of interest (ROIs) from both the static and dynamic perspectives, and fail to reflect the high-level functional connections involving multiple ROIs. Moreover, the feature dimension of the dynamic FCN is excessively high, and there exists a phase mismatch issue between different samples, which renders it impossible to be directly applied to the classification task, and no better solution is available at present. To mitigate these issues, we proposed a comprehensive framework that includes segmenting EEG sequences based on PLI to construct dynamic FCNs;employing seventh-order central moments for feature extraction to form low-order FCNs (Lo-FCNs);and establishing high-order FCNs (Ho-FCNs) based on Pearson correlation theory derived from Lo-FCNs. We conducted classification experiments across four distinct EEG frequency bands using our proposed framework while analyzing relevant features through graph theory and brain topological mapping techniques. The experiments showed that the proposed framework has a high classification accuracy rate in the classification experiments of MDD and NC, and proved the importance of high-order features in classification experiments, indicating that they may serve as physiological markers for MDD diagnosis. © 2024 Copyright held by the owner/author(s).

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Modulated Spike-Time Dependent Plasticity (Stdp)-Based Learning for Spiking Neural Network (Snn): A Review

SSRN

引用

SSRN 2024年

作者： Rahman, Nazeerah Abdul Yusoff, Nooraini Khamis, Nurulaqilla Faculty of Data Science & Computing Universiti Malaysia Kelantan UMK City Campus Pengkalan Chepa Malaysia Institute for Artificial Intelligence & Big Data Universiti Malaysia Kelantan City Campus Pengkalan Chepa Kelantan Kota Bharu16100 Malaysia

Computational models called Spiking Neural Networks (SNNs) are modelled after the intricate information processing discovered in the brain. A key learning principle, spike-time dependent plasticity (STDP), controls how the temporal connection between pre- and post-synaptic spikes affects synaptic weight changes. STDP is a Hebbian learning rule used in training algorithms for SNNs. SNNs encode information in the precise timing of spikes. Modified variants of STDP have recently evolved to improve the learning and adaptation of SNNs. These versions incorporate extra elements like neuromodulators and dendritic processing. This review focuses on the underlying principles, experimental results, and computational models to provide an in-depth overview of the developments in modulated STDP-based learning for SNNs. It also deals with the difficulties of modified STDP, such as computational complexity, parameter optimisation, scalability, and the quest for biological plausibility. This review is invaluable for researchers and practitioners interested in creating practical and biologically plausible learning algorithms for modulated STDP. © 2024, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

A Self-decoupled Interpretable Prediction Framework for Highly-Variable Cloud Workloads 28th

A Self-decoupled Interpretable Prediction Framework for Hig...

引用

28th International Conference on database Systems for Advanced Applications, DASFAA 2023

作者： Wang, Bingchao Shi, Xiaoyu Shang, Mingsheng Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China Chongqing School University of Chinese Academy of Sciences Chongqing400714 China Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing400065 China

ISBN: (纸本)9783031306365

Cloud workloads prediction plays a crucial role in the various tasks of cloud computing, such as resource scheduling, performance optimization, cost management, etc. However, current time series prediction methods suffer instability and inefficiency issues when addressing cloud workloads, due to the high variability of workload patterns and the high fluctuation within a workload. To address these issues, we propose DeIP4CW, a Self-Decoupled Interpretable Prediction framework for highly-variable Cloud Workloads. It can accurately forecast future job arrival rates in a cloud environment. The core idea of DeIP4CW is to first introduce the periodic and residual states as hidden variables to decouple complicated dependencies in cloud workload signals. Then it adopts a deep expansion learning framework with the block structure to perform workload prediction layer by layer. Each block consists of some periodic modules and some compensation modules. The periodic module with a self-attention mechanism can effectively capture the global trend of cloud workload, while the compensation module is employed to compensate for the local volatility information. Moreover, our two customized modules also have interpretable abilities, such as attributing the predictions to either global trends or local compensation. We conduct extensive experiments on the real-world cloud workload traces to evaluate the effectiveness of the proposed DeIP4CW. The experimental results demonstrate the DeIP4CW achieves significant improvements over the best baseline in most cases, and the error reduction can even reach up to 20.66%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Web-Based Optimization and Expansion of Multimodal High School Entrance Examination data Visualization

Web-Based Optimization and Expansion of Multimodal High Scho...

引用

Information and Communication Technology (ICTech), International Conference of

作者： Wei Zhang Duan Jian HongLiang Wang YongHong Zhang Shengyang Institute of Computing Technology University of Chinese Academy of Sciences Beijing China Big Data Technology and Cognitive Intelligence Laboratory Shandong University Beijing China

The reform of the new college entrance examination system makes students and their parents pay more attention to the feasibility and accuracy of the college entrance examination. The college entrance examination informatization can help the local admissions departments to mine and analyze the data rules from the massive college entrance examination data, and provide help and guidance for each link of volunteer application. Therefore, this paper, in order to comply with the development trend of the new college entrance examination information construction, proposes the optimization method of data visualization chart rendering and innovative combination of ideas to improve the Web rendering performance in order to enhance the interactive experience of users and the platform.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rethinking the visual cues in audio-visual speaker extraction

arXiv

引用

arXiv 2023年

作者： Li, Junjie Ge, Meng Pan, Zexu Cao, Rui Wang, Longbiao Dang, Jianwu Zhang, Shiliang Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Department of Electrical and Computer Engineering National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore Shenzhen Research Institute of Big Data Shenzhen China

The Audio-Visual Speaker Extraction (AVSE) algorithm employs parallel video recording to leverage two visual cues, namely speaker identity and synchronization, to enhance performance compared to audio-only algorithms. However, the visual front-end in AVSE is often derived from a pre-trained model or end-to-end trained, making it unclear which visual cue contributes more to the speaker extraction performance. This raises the question of how to better utilize visual cues. To address this issue, we propose two training strategies that decouple the learning of the two visual cues. Our experimental results demonstrate that both visual cues are useful, with the synchronization cue having a higher impact. We introduce a more explainable model, the Decoupled Audio-Visual Speaker Extraction (DAVSE) model, which leverages both visual cues. Copyright © 2023, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

bbTopk: Bandwidth-Aware Sparse Allreduce with Blocked Sparsification for Efficient Distributed Training

bbTopk: Bandwidth-Aware Sparse Allreduce with Blocked Sparsi...

引用

International Conference on Distributed computing Systems

作者： Chang Chen Min Li Chao Yang Center for Data Science Peking University School of Mathematics Sciences Peking University National Engineering Laboratory for Big Data Analysis and Applications Peking University PKU-Changsha Institute for Computing and Digital Economy

Communication overhead is one of the major bottlenecks for large-scale distributed model training. Sparse gradient has been proposed to reduce the communication volume dramatically without affecting the model accuracy. However, high performance implementation of sparse gradient is still hindered by the overheads of gradient sparsification and inefficient implementation of sparse allreduce. For a sparse allreduce operation, the density of intermediate results may dynamically increase as summations progress. Meanwhile, high-performance sparse allreduce is further complicated with heterogeneous bandwidths. To tackle these challenges, we propose bbTopk for efficient sparse gradient training, which includes a new blocked top $k$ sparsification technique and a novel bandwidth-aware sparse allreduce algorithm. In particular, to alleviate the sparsification overhead, we design a blocked top- $k$ method, which can reduce the overhead without sacrificing model accuracy. We then build a heterogeneity-aware communication model combined with the dynamic workload feature of the sparse allreduce. Guided by that, a new sparse allreduce algorithm is proposed that can take advantage of the network resources by improving bandwidth utilization, reducing cross-node hops, and adjusting the round order. Experiments are conducted on a variety of typical neural networks and distributed environments. Results show that bbTopk can substantially outperform the previous state-of-the-art work in most test cases with up to 2.57x speedup while achieving similar accuracy with the dense model empirically.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Activity in Untrimmed Videos Using Dense Optical Flow and Deep Neural Network 5

Early Detection of Activity in Untrimmed Videos Using Dense ...

引用

5th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2021

作者： Poonkodi, M. Vadivu, G. SRM Institute of Science and Technology Department of Computer Science and Engineering Chennai India Big Data Analytics School of Computing SRM Institute of Science and Technology Chennai India

ISBN: (纸本)9781665435246

Computer Vision is playing aremarkable role right from essentials to entertainment and thus trying to turn computer as a 'seeing' machine. Having widespread applications in most of the real world domain like healthcare, surveillance., space and social media, yet it is still challenging to match human intelligence in understanding the underlying context. Recognition of a task performed by human is important to learn the happenings, but predicting it, from the activities' initial subset becomes an aid to overcome adversities in near future. Numerous algorithms and techniques are present, yet a gap exists due to the environment in which it is recorded, illumination condition,overlapping of men and materials on captured scenes *** lead to the requirement of high power computing devices for recognition, which is considerably *** this work, Dense OPnet (Dense optical flow and Convolution neural Net) is proposed which takes in the RGB input video, converted to dense optical flow frames and then fed to three layered CNN for recognition and early detection of an activity using N/2 frames of the total input video. This method is evaluated on two benchmark datasetlike J-HMDB21 and UCF50 giving an accuracy of 93.4% and 74.3% on recognition, 68.2% and 50.24% on early action detection respectively. © 2021 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Research on Technologies in data Fabric

Research on Technologies in Data Fabric

引用

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Qingyuan Hu Zheng Yin Tao Tao Jibin Wang Zhuo Chen Bohuan Ai Yu Liu Chongzhou Liu China Mobile Information Technology Center Beijing China Cloud Computing and Big Data Research Institute China Academy of Information and Communications Technology Beijing China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

With the continuous advancement of technologies like big data, artificial intelligence, and cloud computing, enterprises are increasingly encountering challenges related to the heterogeneity of data from various sources, difficulties in querying data assets, and understanding business insights. To address these issues, data fabric emerges as a solution that leverages distributed data management. By harnessing metadata and facilitating its activation, data fabric enables organizations to efficiently and accurately manage and locate data assets. However, it is important to note that this concept is still under development and faces obstacles such as establishing connections with additional data sources and unifying semantics. Nonetheless, overall, the concept of data fabric exhibits remarkable potential in assisting enterprises in transitioning towards becoming data-driven organizations.

关键词： Industries Cloud computing Technological innovation Soft sensors Standards organizations Distributed databases Collaboration

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: Boosting Can Achieve Modality Reconcilement 41

ReconBoost: Boosting Can Achieve Modality Reconcilement

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

CAAVM-TransUNet: Integrating Context Anchor Attention with Transformer U-Net for Single Image Dehazing

CAAVM-TransUNet: Integrating Context Anchor Attention with T...

引用

International Conference on Computer and Communications (ICCC)

作者： Hongwei Zeng Lijun Fu Jin Li Xu Li Xiangdong He Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang China Laboratory of Big Data and Artificial Intelligence Technolgy Shandong University Jinan China Institute of Future Artificial Intelligence Technology and Innovative Applications Beijing China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

Image dehazing has always been a challenging visual task. Most of the existing image dehazing algorithms are constructed based on convolutional neural networks, which perform very well in capturing local features and detail information, but fall short of the ability to capture remote contextual information. In this paper, we introduce a novel method called CAAVM-TransUNet. The method integrates Transformer into the traditional U -shaped architecture. Unlike earlier Transformer-based U-Net, CAA VM-TransUNet introduces the State Space Sequence Model (SSM) to enhance the ability of capturing remote dependencies, and adds Context Anchor Attention (CAA) to filter redundant features in the hopping connectivity layer prior to the encoder and decoder, so that the model can better focus on the key feature information and reduce the interference of irrelevant information, thus improving the effect of image dehazing. The results show that the dehazing effect of CAAVM-TransUNet on RESIDE dataset is better than the existing methods, especially the PSNR in the SOTS-outdoor dataset reaches 36.13 dB, which provides a new idea to solve the complex image dehazing problem.

关键词： Visualization PSNR Interference Drives Transformers Information filters Decoding Environmental monitoring Convolutional neural networks Context modeling

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：