检索结果-内蒙古大学图书馆

21st International computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2024

作者： Renxiang, Huang Jia, Chen Jianping, Li School of Artificial Intelligence and Big Data Sichuan University of Arts and Science Chengdu635002 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9798331519254

This paper reviews the research progress of deep learning-based household waste classification algorithms. It first introduces the importance of household waste classification and the application value of deep learning in this field. Next, it outlines the theoretical foundations of deep learning technology in waste classification, including the principles of convolutional neural networks and their applications in image recognition. The article provides a detailed analysis of the application of different deep learning models in waste classification, such as MobileNetV2, ShuffleNetV1, EfficientNetV1, and YOLOV5, as well as their optimizations and innovations in practical applications. Furthermore, it discusses optimization and innovation methods for deep learning models, including learning rate adjustment, optimizer selection, attention mechanisms, data augmentation, and lightweight network design. Finally, it summarizes the current research shortcomings and challenges, and looks forward to future research directions. This review provides a systematic perspective for a deeper understanding of the application of deep learning in waste classification and offers directions for future research. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving the Utility of Differentially Private SGD by Employing Wavelet Transforms

Improving the Utility of Differentially Private SGD by Emplo...

引用

2023 IEEE International Conference on Big data, Bigdata 2023

作者： Ranaweera, Kanishka Smith, David Nguyen, Dinh C. Pathirana, Pubudu N. Ding, Ming Rakotoarivelo, Thierry Seneviratne, Aruna Deakin University School of Engineering Australia Data61 Csiro Australia The University of Alabama in Huntsville Department of Electrical and Computer Engineering United States School of Electrical Engineering and Telecommunications Unsw Australia

ISBN: (纸本)9798350324457

Deep learning (DL) has become a powerful tool in many areas of research and industry, ranging from computer vision to natural language processing. Nonetheless, as DL models are trained on large amounts of sensitive data, concerns about data privacy have emerged. In light of this, differential privacy (DP) has emerged as a promising technique that provides strong privacy guarantees while allowing useful information to be extracted from the data. DP involves adding random noise to the training data or model parameters, which makes it difficult for an attacker to identify the contribution of any single data point to the final model. Despite the promising results, DP can significantly degrade the performance of DL models, especially when dealing with large datasets or complex models. To improve the balance between privacy and utility, this paper proposes a novel modification to the vanilla DP algorithm that uses a Haar wavelet transform. The proposed method achieves better utility while maintaining the same (ϵ, δ) privacy guarantees as vanilla DP algorithms. The paper provides an analytical demonstration of the improved noise variance bounds compared to previous methods. The paper also provides a detailed analysis of the convergence performance of the proposed algorithm and shows that the Haar wavelet transform improves the accuracy and efficiency of the training process. The experimental evaluation demonstrates that the proposed method outperforms state-of-the-art algorithms on four widely used scientific benchmark datasets making this a significant contribution to DP techniques' practical applications in DL. © 2023 IEEE.

关键词： deep learning differential privacy wavelet transform

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep Learning Framework for Stock Price Forecasting with Sentimental Analysis 13

A Hybrid Deep Learning Framework for Stock Price Forecasting...

引用

13th International Conference on System Modeling and Advancement in Research Trends, SMART 2024

作者： Banoth, Shobhan Yadala, Sucharitha Vice President-Data/Information Management Lead Engineer Citi Bank United States School of Computer Science and Engineering Vnr Vignana Jyothi Institute of Engineering & Technology Telangana Hyderabad India

ISBN: (纸本)9798350380583

Social media electronic word-of-mouth data affects stock market confidence and trading. As a result, stock market sentiment research of comments is essential for stock market forecasting. Unfortunately, English is becoming the de facto language for sentiment analysis. This study translates writings from places where English is not the local language into English so that multilingual sentiment analysis can be performed. In order to predict stock market movements, this research combined social media's unstructured data with structured data, such as transaction records and technical indicators. Parameter determination has a significant impact on the effectiveness of forecasting models;in recent years, deep-learning(DL) and machine-learning(ML) models have developed as effective means of dealing with anticipating issues. In order to anticipate stock market indices and business stock prices using hybrid data in places where English is not the native language, this research utilized Long-Short-Term Memory(LSTM) models that utilized the geneticalgorithm(GA) to choose parameters. The created LSTMGA model outperformed the other ML-strategies with different types of data in terms of accuracy when it came to generating forecasts using hybrid multilingual sentiment data. As a result, the stock market forecasting method that combines the suggested LSTMGA model with hybrid sentiment analysis is both practical and encouraging. © 2024 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Fast Parallel Recovery for Transactional Stream Processing on Multicores 40

Fast Parallel Recovery for Transactional Stream Processing o...

引用

40th IEEE International Conference on data engineering, ICDE 2024

作者： Zhao, Jianjun Liu, Haikun Zhang, Shuhao Duan, Zhuohui Liao, Xiaofei Jin, Hai Zhang, Yu School of Computer Science and Technology Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (纸本)9798350317152

Transactional stream processing engines (TSPEs) have gained increasing attention due to their capability of processing real-time stream applications with transactional semantics. However, TSPEs remain susceptible to system failures and power outages. Existing TSPEs mainly focus on performance improvement, but still face a significant challenge to guarantee fault tolerance while offering high-performance services. We revisit commonly-used fault tolerance approaches in stream processing and database systems, and find that these approaches do not work well on TSPEs due to complex data dependencies. In this paper, we propose a novel TSPE called MorphStreamR to achieve fast failure recovery while guaranteeing low performance overhead at runtime. The key idea of MorphStreamR is to record intermediate results of resolved dependencies at runtime, and thus eliminate data dependencies to improve task parallelism during failure recovery. MorphStreamR further mitigates the runtime overhead by selectively tracking data dependencies and incorporating workload-aware log commitment. Experimental results show that MorphStreamR can significantly reduce the recovery time by up to 3.1 x while experiencing much less performance slowdown at runtime, compared with other applicable fault tolerance approaches. © 2024 IEEE.

关键词： Fault tolerance

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

GACP:graph neural networks with ARMA flters and a parallel CNN for hyperspectral image classification

引用

International Journal of Digital Earth 2023年第1期16卷 1770-1800页

作者： Jing Yang Jie Sun Yaping Ren Shaobo Li Shujie Ding Jianjun Hu School of Mechanical Engineering Guizhou UniversityGuiyangPeople’s Republic of China State Key Laboratory of Public Big Data Guizhou UniversityGuiyangPeople’s Republic of China School of Intelligent Systems Science and Engineering Jinan UniversityZhuhaiPeople’s Republic of China Department of Computer Science and Engineering University of South CarolinaColumbiaSCUSA

In recent years,the use of convolutional neural networks(CNNs)and graph neural networks(GNNs)to identify hyperspectral images(HSIs)has achieved excellent results,and such methods are widely used in agricultural remote sensing,geological exploration,and marine remote *** many generalization classification algorithms are designed for the purpose of learning a small number of samples,there is often a problem of a low utilization rate of position information in the empty spectral *** on this,a GNN with an autoregressive moving average(ARMA)-based smoothingfilter samples the node information in the null spectral domain and then captures the spatial information at the pixel level via spatial feature convolution;then,the null spectral domain position information lost by the CNN is located by a coordinate attention(CA)***,autoregressive,spatial convolution,and CA mechanisms are combined into multiscale features to enhance the learning capacity of the network for tiny *** conducted on the widely used Indian Pines(IP)dataset,the Botswana(BS)dataset,Houton 2013(H2013),and the WHU-Hi-HongHu(WHU)benchmark HSI dataset demonstrate that the proposed GACP technique can perform classification work with good accuracy even with a small number of training examples.

关键词： Graph neural networks word convolutional neural networks hyperspectral image classification attention mechanisms

来源：评论

学校读者我要写书评

暂无评论

TROPICAL: Transformer-Based Hypergraph Learning for Camouflaged Fraudster Detection 24

TROPICAL: Transformer-Based Hypergraph Learning for Camoufla...

引用

24th IEEE International Conference on data Mining, ICDM 2024

作者： Haghighi, Venus Soltani, Behnaz Shabani, Nasrin Wu, Jia Zhang, Yang Yao, Lina Sheng, Quan Z. Yang, Jian School of Computing Macquarie University SydneyNSW2109 Australia School of Computer Science and Engineering University of New South Wales NSW Australia CSIRO's Data61 Australia

ISBN: (纸本)9798331506681

Graph-based fraud detection has attracted increasing attention in recent years, reflecting its growing potential in mitigating sophisticated fraudulent activities. The main objective of graph-based fraud detection is to discern between fraud-sters and normal entities within graphs. As fraudsters adopt increasingly sophisticated camouflage tactics, combating them has become an urgent task. Despite the complex interactions within real-world networks involving high-order relations, ex-isting graph-based fraud detection methods often neglect non-pairwise relationships among entities in graphs. Thus, we empha-size the significance of investigating beyond pairwise relationships for building an effective fraud detection model. In this paper, we propose constructing a hypergraph from the original input graph to encapsulate comprehensive high-order relations and present TROPICAL, a novel TRansfOrmer-based hyPergraph LearnIng for detecting CAmouflaged maLicious actors in online social networks. TROPICAL learns representations by processing different hyperedge groups and incorporates positional encodings into the aggregated information to enhance their distinctiveness. Subsequently, the model feeds the learned aggregated sequential information into the transformer encoder, achieving rich rep-resentations for effective camouflaged fraudster detection. The superiority of TROPICAL is demonstrated through experiments conducted on two real-world datasets, compared against the state-of-the-art fraud detection models. The source codes and datasets of our work are available at https://***/TROPICAL. © 2024 IEEE.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Flow-Guided Deformable Alignment Network with Self-Supervision for Video Inpainting 48

Flow-Guided Deformable Alignment Network with Self-Supervisi...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Wu, Zhiliang Zhang, Kang Sun, Changchang Xuan, Hanyu Yan, Yan Nanjing University of Science and Technology School of Computer Science and Engineering China Illinois Institute of Technology Department of Computer Science United States Anhui University School of Big Data and Statistics China

ISBN: (纸本)9781728163277

Video inpainting aims to utilize plausible contents to fill missing regions in the video. State-of-the-art video inpainting methods typically generate the missing contents of the target frame (current frame) by aggregating the temporal information of reference frames (neighboring frames) aligned using deformable convolution. However, these deformable convolution alignment networks often suffer from offset overflow during training, resulting in unsatisfactory alignment, thereby obtaining compromised inpainting performance. In this paper, we propose a self-supervised Flow-Guided Deformable Alignment (FGDA) network for aligning reference frames at the feature level. FGDA computes the residual of the optical flow as the offsets. This design can effectively reduce the burden of offsets learning, thereby avoiding offset overflow. Furthermore, a gradient-weighted reconstruction loss for supervised completed frame reconstruction is designed, which can use the gradients in all directions of the video frame to emphasize the difficultly reconstructed texture regions, so that detail textures get more attention during training. Experiments show that FGDA-based video inpainting model trained with gradient-weighted reconstruction loss outperforms the state-of-the-art by a significant margin in terms of PSNR and SSIM with relative improvements of 6.2% and 2.1%, respectively. © 2023 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

MG-Net: Learn to Customize QAOA with Circuit Depth Awareness 38

MG-Net: Learn to Customize QAOA with Circuit Depth Awareness

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Qian, Yang Wang, Xinbiao Du, Yuxuan Luo, Yong Tao, Dacheng School of Computer Science Faculty of Engineering University of Sydney NSW2008 Australia Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore

Quantum Approximate Optimization Algorithm (QAOA) and its variants exhibit immense potential in tackling combinatorial optimization challenges. However, their practical realization confronts a dilemma: the requisite circuit depth for satisfactory performance is problem-specific and often exceeds the maximum capability of current quantum devices. To address this dilemma, here we first analyze the convergence behavior of QAOA, uncovering the origins of this dilemma and elucidating the intricate relationship between the employed mixer Hamiltonian, the specific problem at hand, and the permissible maximum circuit depth. Harnessing this understanding, we introduce the Mixer Generator Network (MG-Net), a unified deep learning framework adept at dynamically formulating optimal mixer Hamiltonians tailored to distinct tasks and circuit depths. Systematic simulations, encompassing Ising models and weighted Max-Cut instances with up to 64 qubits, substantiate our theoretical findings, highlighting MG-Net's superior performance in terms of both approximation ratio and efficiency. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neurodynamic Mapping for Cybersickness Prediction in 3D Game Immersion 5

Neurodynamic Mapping for Cybersickness Prediction in 3D Game...

引用

5th International Conference on Emerging Systems and Intelligent Computing, ESIC 2025

作者： Balaji, C. Mishra, Shruti Satapathy, Sandeep Kumar Vellore Institute of Technology School of Computer Science and Engineering Tamil Nadu Chennai India Vellore Institute of Technology Centre for Advanced Data Science Tamil Nadu Chennai India

ISBN: (纸本)9798331522100

The rapid expansion of virtual reality (VR) applications in gaming and training has highlighted cybersickness, a condition marked by symptoms such as nausea, dizziness, and disorientation. Traditional assessment methods often rely on subjective reporting, which hampers timely intervention. This study aims to develop a novel approach for predicting the onset of cybersickness through neurodynamic mapping of electroencephalogram (EEG) data and heart rate variability (HRV) in immersive 3D VR environments. Spiking neural network (SNN) architecture to analyze integrated EEG and HRV data collected from participants engaged in 3D VR games. Key EEG channels, particularly F7, Cz, and O2, were identified as critical biomarkers for susceptibility to cybersickness. Real-time monitoring of brainwave frequencies (delta, theta, alpha, and beta) enabled tracking of changes associated with symptom onset. SNN model achieved a prediction accuracy of 85.9% at resting baseline conditions and detected cybersickness events with an accuracy of 76.6%. The dynamic characteristics of the identified biomarkers suggest potential for enhancing prediction models over time. This research introduces a groundbreaking method for predicting cybersickness in VR gaming by leveraging neurodynamic mapping and SNNs. Our findings provide insights into the neural mechanisms underlying VR-induced motion sickness and have significant implications for improving user experience across various applications, including gaming and virtual therapy. The integration of neurodynamic feedback systems could foster more immersive and user-friendly VR environments by facilitating timely interventions to mitigate cybersickness. © 2025 IEEE.

关键词： Volume rendering

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：